INTERNATIONAL JOURNAL OF LATEST TECHNOLOGY IN ENGINEERING,

MANAGEMENT & APPLIED SCIENCE (IJLTEMAS)

ISSN 2278-2540 | DOI: 10.51583/IJLTEMAS | Volume XIII, Issue VI, June 2024

www.ijltemas.in Page 13

recruiters to find qualified applicants quickly. This study presents an innovative method to integrate artificial

intelligence techniques into a custom application to expedite the resume screening process. The program increases the

effectiveness of recruitment workflows by a webapp that can be created to take inputs in form of pdf or csv format from

the user and screens the resume. The development of a prototype application is the first step in the research

methodology. It is then thoroughly verified and analyzed.

The initial phase in the hiring process is resume screening, during which recruiters or hiring managers go through an

extensive collection of resumes in looking for qualified applicants for a position. It entails reviewing each resume to

ascertain whether the candidate has the education, training, and work history needed for the role.

They play a vital role in the hiring process due to increased volume of the received applications. Further subject

expertise is needed for the screening process in order to comprehend the requirements and eligibility for the employment

Contract or Freelance Work: Although projects involving flexibility and a wide range of skills might be demonstrated,

resume screening applications could find it difficult to assess the value or applicability of such experiences. Applicants

who have chosen alternative career paths may be at a disadvantage as they may give preference to applicants with

traditional job history over those on contract.

Non-Traditional Education and Skills Development: Resume screening tools that give preference to degrees from

INTERNATIONAL JOURNAL OF LATEST TECHNOLOGY IN ENGINEERING,

MANAGEMENT & APPLIED SCIENCE (IJLTEMAS)

ISSN 2278-2540 | DOI: 10.51583/IJLTEMAS | Volume XIII, Issue VI, June 2024

www.ijltemas.in Page 14

This particular problem comes under transfer learning which refers to using a model trained for one task in a different application

than what it was generally trained for.

In zero shot classification we provide the model with a prompt and a sequence of text that describes what we want our model to do,

in natural language.

By importing Regular expression library, we can use it for Data Cleaning by replacing special characters, non-ASCII characters,

INTERNATIONAL JOURNAL OF LATEST TECHNOLOGY IN ENGINEERING,

MANAGEMENT & APPLIED SCIENCE (IJLTEMAS)

ISSN 2278-2540 | DOI: 10.51583/IJLTEMAS | Volume XIII, Issue VI, June 2024

www.ijltemas.in Page 15

StreamLit is an open-source python library that facilitates the development and dissemination of stunning, unique online applications

for data science and machine learning. It takes only a few minutes to create and implement robust data applications.

For the resume screening project, the web application can come very useful as users may submit resumes straight into the program

with StreamLit’ s user friendly interface.

Just by submitting the 2 inputs which are labels and resume we can predict the scores of labels suited for the resume.

Scenario 1: When input is a data science resume and input labels provided are machine learning engineer and software developer.

We can see that software developer is a highly suitable job compared to the rest of the labels.

Hence, we can see that zero-shot classification can definitely help us in screening of resumes. After integration of this model with

web or app development it can turn into a large-scale application which can ease the burden of the recruiters as they will not have to

manually view a flood of resumes.

INTERNATIONAL JOURNAL OF LATEST TECHNOLOGY IN ENGINEERING,

MANAGEMENT & APPLIED SCIENCE (IJLTEMAS)

ISSN 2278-2540 | DOI: 10.51583/IJLTEMAS | Volume XIII, Issue VI, June 2024

www.ijltemas.in Page 16

1. Jie Chen, Chunxia Zhang and Zhendong Niu, "A Two- Step Resume Information Extraction Algorithm", Mathematical

Problems in Engineering, vol. 2018, pp. 8, 2018.

2. Kajal Kumari, Resume Screening with Natural Language Processing in Python, June 2021.

3. T Schmitt, P Caillou and M Sebag, "Matching Jobs and Resumes: a Deep Collaborative Filtering Task", Proc. of the 2nd

Global Conf. on Artificial Intelligence, pp. 1-14, 2016.

7. J Chen, Z Niu and H Fu, "A Novel Knowledge Extraction Framework for Resumes Based on Text Classifier", Proceedings

of the International Conference on Web-Age Information Management, pp. 540-543, 2015

8. A. Zaroor, M. Maree and M. Sabha, "A Hybrid Approach to Conceptual Classification and Ranking of Resumes and Their

Corresponding Job Posts" in IDT 2017. Smart Innovation Systems and Technologies, Cham:Springer, vol. 72, 2017

9. Arvind Sinha, Amir Khusru and Ashwani Kumar, "Resume Screening Using Natural Language Processing and Machine

Learning: A Systematic Review", Machine Learning and Information Processing Advances in Intelligent Systems and

Computing, vol. 1311, 2021.

10. Yasunobu Kinoa, Hiroshi Kurokia, Tomomi Machidab, Norio Furuyab and Kanako Takano, "Text Analysis for Job

Matching Quality Improvement", International Conference on Knowledge Based and Intelligent Information and

Engineering Systems Procedia Computer Science, vol. 112, pp. 1523-1530, 2017.

11. Pradeep Roy, Sarabjeet Chowdhary and Rocky Bhatia, "A Machine Learning approach for automation of Resume

15. S. Antol, C. Zitnick and D. Parikh, "Zero-shot learning via visual abstraction", Proceedings of ECCV, 2014.